Challenge: Large language models (LLMs) have shown remarkable achievements across various language tasks.
Approach: They propose a scientific literature LLM and a knowledge service system based on it . they collect scientific literature and then pre-train it using autoregressive training .
Outcome: The proposed system provides literature investigation, paper reading, and academic writing functions.

Similar Papers

SciLit: A Platform for Joint Scientific Literature Discovery, Summarization and Citation Generation (2023.acl-demo)

Copied to clipboard

Challenge: Scientific writing involves retrieving, summarizing, and citing relevant papers.
Approach: They propose a pipeline that automatically recommends relevant papers, extracts highlights, and suggests a reference sentence as a citation of a paper.
Outcome: The proposed pipeline recommends relevant papers from large databases of hundreds of millions of papers . it provides extractive summaries and abstractively-generated citation sentences . authors question whether it is possible to partly automate this process to reduce cognitive load .
SciRIFF: A Resource to Enhance Language Model Instruction-Following over Scientific Literature (2025.emnlp-main)

Copied to clipboard

Challenge: ScIRIFF is the only entirely expert-written instruction-following dataset for scientific literature understanding . it features complex instructions with long input contexts, detailed task descriptions, and structured outputs.
Approach: They present a dataset of 137K instruction-following instances for training and evaluation . they finetuned large language models using a mix of general domain and ScIRIFF instructions .
Outcome: The proposed dataset shows that on nine out-of-distribution held-out tasks, the model performs better than baselines trained on general domain instructions.
A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery (2024.emnlp-main)

Copied to clipboard

Challenge: Existing surveys on scientific LLMs focus on one or two fields or a single modality.
Approach: They survey 260 scientific LLMs and examine their architectures and pre-training techniques . they also discuss commonalities and differences between LLM architectures .
Outcome: The proposed model architectures and evaluation techniques are used to improve scientific discovery.
ESRA: Explainable Scientific Research Assistant (2021.acl-demo)

Copied to clipboard

Challenge: Existing literature search systems only present metadata of papers as search results, which requires users to read the entire abstracts to understand the brief contents of the returned papers.
Approach: They propose to use a knowledge graph extracted from abstracts of 23k papers on arXiv’s cs.CL category to augment search results with relevant details and explanations.
Outcome: The proposed platform can accelerate the users’ search process with paper explanations and helps them better explore the landscape of the topics of interest.
CASE: Large Scale Topic Exploitation for Decision Support Systems (2025.coling-demos)

Copied to clipboard

Challenge: Topic models are still a major tool for information retrieval and summarization, but their integration into decision-making systems is limited.
Approach: They propose a tool for exploiting topic information for semantic analysis of large corpora using a Solr engine and a customized indexing strategy.
Outcome: The proposed approach can be used to analyze large corpora and perform thematic trend analysis, topic-based document retrieval, or similarity search.
Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation (2025.naacl-long)

Copied to clipboard

Challenge: Recent advances in Large Language Models (LLMs) have significantly enhanced their capabilities across various cognitive tasks.
Approach: They propose a high-quality evaluation dataset to test LLMs' ability to provide factual responses, assess retrieval capabilities, and evaluate the reasoning required to generate final answers.
Outcome: The proposed framework improves performance in end-to-end RAG scenarios.
FiDeLiS: Faithful Reasoning in Large Language Models for Knowledge Graph Question Answering (2025.findings-acl)

Copied to clipboard

Challenge: Existing retrieval-based or agent-based methods are prone to generating erroneous or hallucinated outputs.
Approach: They propose a framework to leverage knowledge graphs as external knowledge sources to improve the factuality of LLM responses by anchoring answers to verifiable reasoning steps retrieved from KGs.
Outcome: The proposed framework improves factuality and interpretability across benchmarks and reduces computational costs.
Large Language Models for Generative Recommendation: A Survey and Visionary Discussions (2024.lrec-main)

Copied to clipboard

Challenge: Large language models (LLMs) have revolutionized the field of natural language processing but are not fully able to leverage the generative power of LLM.
Approach: They examine the progress, methods, and future directions of large language models . they examine what generative recommendation is, why RS should advance to generative recommendations .
Outcome: The proposed approach can be simplified to generate recommendations from the entire pool of items.
RaLLe: A Framework for Developing and Evaluating Retrieval-Augmented Large Language Models (2023.emnlp-demo)

Copied to clipboard

Challenge: Existing libraries for building R-LLMs provide high-level abstractions without sufficient transparency for evaluating and optimizing prompts within specific inference processes.
Approach: They propose an open-source framework to facilitate the development, evaluation, and optimization of R-LLMs for knowledge-intensive tasks.
Outcome: The framework improves hand-crafted prompts, inference processes and quantitatively measures overall system performance.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations